Balancing Multimodal Training Through Game-Theoretic Regularization

• URL: http://arxiv.org/abs/2411.07335v3
• Date: Wed, 01 Oct 2025 13:03:01 GMT
• Title: Balancing Multimodal Training Through Game-Theoretic Regularization
• Authors: Konstantinos Kontras, Thomas Strypsteen, Christos Chatzichristos, Paul Pu Liang, Matthew Blaschko, Maarten De Vos,
• Abstract summary: Multimodal learning holds promise for richer information extraction by capturing dependencies across data sources.<n>Yet, current training methods often underperform due to modality competition.<n>This paper proposes the Multimodal Competition Regularizer (MCR), inspired by a mutual information (MI) decomposition.
• Score: 26.900302082724295
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multimodal learning holds promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality competition, a phenomenon where modalities contend for training resources leaving some underoptimized. This raises a pivotal question: how can we address training imbalances, ensure adequate optimization across all modalities, and achieve consistent performance improvements as we transition from unimodal to multimodal data? This paper proposes the Multimodal Competition Regularizer (MCR), inspired by a mutual information (MI) decomposition designed to prevent the adverse effects of competition in multimodal training. Our key contributions are: 1) A game-theoretic framework that adaptively balances modality contributions by encouraging each to maximize its informative role in the final prediction 2) Refining lower and upper bounds for each MI term to enhance the extraction of both task- relevant unique and shared information across modalities. 3) Proposing latent space permutations for conditional MI estimation, significantly improving computational efficiency. MCR outperforms all previously suggested training strategies and simple baseline, clearly demonstrating that training modalities jointly leads to important performance gains on both synthetic and large real-world datasets. We release our code and models at https://github.com/kkontras/MCR.

Related papers

• Bagging-Based Model Merging for Robust General Text Embeddings [73.51674133699196]
  General-purpose text embedding models underpin a wide range of NLP and information retrieval applications.<n>We present a systematic study of multi-task training for text embeddings from two perspectives: data scheduling and model merging.<n>We propose Bagging-based rObust mOdel Merging (BOOM), which trains multiple embedding models on sampled subsets and merges them into a single model.
  arXiv  Detail & Related papers  (2026-02-05T15:45:08Z)
• Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process [55.91649771370862]
  Dirichlet process (DP) mixture model is a powerful non-parametric method that can amplify the most prominent features.<n>We propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment.
  arXiv  Detail & Related papers  (2025-10-23T16:53:24Z)
• MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning [47.487732221767196]
  We present Modality-Informed Learning ratE Scheduler (MILES) for training multimodal joint fusion models.<n>MILES balances modality-wise conditional utilization rates during training to effectively balance multimodal learning.<n>Our results show that MILES outperforms all baselines across all tasks and fusion methods considered in our study.
  arXiv  Detail & Related papers  (2025-10-20T10:34:59Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• A Robust Incomplete Multimodal Low-Rank Adaptation Approach for Emotion Recognition [17.332141776831513]
  Multimodal Emotion Recognition (MER) often encounters incomplete multimodality in practical applications.<n>We propose a unimodal decoupled dynamic low-rank adaptation method based on modality combinations, named MCULoRA.
  arXiv  Detail & Related papers  (2025-07-15T11:15:35Z)
• Improving Multimodal Learning Balance and Sufficiency through Data Remixing [14.282792733217653]
  Methods for enforcing the weak modality fail to achieve unimodal sufficiency and multimodal balance.<n>We propose multimodal Data Remixing, including decoupling multimodal data and filtering hard samples for each modality to mitigate modality imbalance.<n>Our method can be seamlessly integrated with existing approaches, improving accuracy by approximately 6.50%$uparrow$ on CREMAD and 3.41%$uparrow$ on Kinetic-Sounds.
  arXiv  Detail & Related papers  (2025-06-13T08:01:29Z)
• Learning Optimal Multimodal Information Bottleneck Representations [5.823241063353844]
  We propose a novel multimodal learning framework, Optimal Multimodal Information Bottleneck (OMIB)<n>OMIB guarantees the achievability of optimal MIB by setting the regularization weight within a theoretically derived bound.<n>We empirically validate the OMIB's theoretical properties on synthetic data and demonstrate its superiority over the state-of-the-art benchmark methods in various downstream tasks.
  arXiv  Detail & Related papers  (2025-05-26T13:48:07Z)
• The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models [31.81567038783558]
  Multimodal Reward Models (MM-RMs) are crucial for aligning Large Language Models (LLMs) with human preferences. MM-RMs often struggle to generalize to out-of-distribution data due to their reliance on unimodal spurious correlations. We introduce a Shortcut-aware MM-RM learning algorithm that mitigates this issue by dynamically reweighting training samples.
  arXiv  Detail & Related papers  (2025-03-05T02:37:41Z)
• Asymmetric Reinforcing against Multi-modal Representation Bias [59.685072206359855]
  We propose an Asymmetric Reinforcing method against Multimodal representation bias (ARM) Our ARM dynamically reinforces the weak modalities while maintaining the ability to represent dominant modalities through conditional mutual information. We have significantly improved the performance of multimodal learning, making notable progress in mitigating imbalanced multimodal learning.
  arXiv  Detail & Related papers  (2025-01-02T13:00:06Z)
• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach [29.428067329993173]
  We propose a modality invariant multimodal learning method, which is less susceptible to the impact of missing modalities. It consists of a single-branch network sharing weights across multiple modalities to learn inter-modality representations to maximize performance. Our proposed method achieves superior performance when all modalities are present as well as in the case of missing modalities during training or testing compared to the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-14T10:32:16Z)
• Modality-Balanced Learning for Multimedia Recommendation [21.772064939915214]
  We propose a Counterfactual Knowledge Distillation method to solve the imbalance problem and make the best use of all modalities. We also design a novel generic-and-specific distillation loss to guide the multimodal student to learn wider-and-deeper knowledge from teachers. Our method could serve as a plug-and-play module for both late-fusion and early-fusion backbones.
  arXiv  Detail & Related papers  (2024-07-26T07:53:01Z)
• Multimodal Representation Learning by Alternating Unimodal Adaptation [73.15829571740866]
  We propose MLA (Multimodal Learning with Alternating Unimodal Adaptation) to overcome challenges where some modalities appear more dominant than others during multimodal learning. MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process. It captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities. Experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities.
  arXiv  Detail & Related papers  (2023-11-17T18:57:40Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)
• Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models [51.5543321122664]
  This paper investigates how to better leverage large-scale pre-trained uni-modal models to enhance discriminative multi-modal learning. We introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA)
  arXiv  Detail & Related papers  (2023-10-08T15:01:54Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning [21.822251958013737]
  We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets.
  arXiv  Detail & Related papers  (2023-05-02T07:15:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.